Title: Computational prediction of toxicity

Authors: Meenakshi Mishra; Hongliang Fei; Jun Huan

Addresses: Department of Electrical Engineering and Computer Science, University of Kansas, Lawrence, 66047-7621 KS, USA ' Department of Electrical Engineering and Computer Science, University of Kansas, Lawrence, 66047-7621 KS, USA ' Department of Electrical Engineering and Computer Science, University of Kansas, Lawrence, 66047-7621 KS, USA

Abstract: With increasing number of chemicals produced each year, it still remains a daunting task to keep up with the toxicity profile of each chemical. In this paper, we attempt to predict toxicity of compounds using computational techniques, where results from certain in vitro assays applied on 309 chemicals, along with computed properties of chemicals are used to predict the toxicity caused by them at a particular endpoint. We show that both Random Forest (RF) and Naïve Bayes (NB) have a good performance. We also show that using small and related trees in RF helps to further improve the performance.

Keywords: toxicity prediction; random forest; machine learning; computational prediction; EPA; TOXCAST; computational learning methods; L1 norm; L2 norm; graph boosting; bioinformatics; chemicals; chemical toxicity; naive Bayes.

DOI: 10.1504/IJDMB.2013.056082

International Journal of Data Mining and Bioinformatics, 2013 Vol.8 No.3, pp.338 - 348

Received: 09 May 2011
Accepted: 09 May 2011
Published online: 20 Oct 2014 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article